How to improve intensity contrast in image? - image

Question

I have an image with very low intensity contrast from its background.
The first line between the two arrows is the line with low contrast.
The second line is ok. Please see in the below image.
The original image is as shown below.
I used the following method to enhance the contrast in Gray scale.
First the image is changed to Gray color and used the following method.
cv::Mat temp;
for (int i = 0; i < 1; i++) // number of iterations has to be adjusted
{
cv::threshold(image, temp, 0, 255, CV_THRESH_BINARY| CV_THRESH_OTSU);//
cv::bitwise_and(image, temp, image);
cv::normalize(image, image, 0, 255, cv::NORM_MINMAX, -1, temp);
}
I have image with a little bit higher in contrast in Gray scale, but is there any method better than this in Gray scale or Color?

Answer 1

I would look at histogram equalization, that might serve your needs. Basic (global) equalization or even adaptive can yield great results. Parameters will likely need to be tuned for the adaptive method (using the one from the docs example for now).
I get (global equalization - left; adaptive equalization - right):
Once the equalization is done, you might have better luck with thresholding (though your example is very low contrast):
From there, you can use standard contour/shape matching etc to try to find the location of your 1st black line.
Gotten from
import cv2
import matplotlib.pyplot as plt
import numpy as np
raw_img_load = cv2.imread('H1o8X.png')
imgr = cv2.cvtColor(raw_img_load,cv2.COLOR_BGR2GRAY)
clahe = cv2.createCLAHE(clipLimit=30.0, tileGridSize=(8,8))
imgray_ad = clahe.apply(imgr)#adaptive
imgray = cv2.equalizeHist(imgr)#global
res = np.hstack((imgray,imgray_ad))#so we can plot together
plt.imshow(res,cmap='gray')
plt.show()
ret,thresh = cv2.threshold(imgray_ad,150,255,type=cv2.THRESH_BINARY+cv2.THRESH_OTSU)
plt.imshow(thresh,cmap='gray')
plt.show()
EDIT: based on #Doleron's answer, for this particular problem I would recommend using fastNlMeansDenoising (applied before any histogram equalization). Note, however, that it can be a slow function for high-res images/time-sensitive image processing.

Answer 2

The #Antoine Zambelli answer is awsome and it is the correct one. Anyway, I dug some here and and tried to remove the noise previously with fastNlMeansDenoising to improve the final result:
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include "opencv2/photo.hpp"
using namespace cv;
using cv::CLAHE;
int main(int argc, char** argv) {
Mat srcImage = imread("H1o8X.png", CV_LOAD_IMAGE_GRAYSCALE);
imshow("src", srcImage);
Mat denoised;
fastNlMeansDenoising(srcImage, denoised, 10);
Mat image = denoised;
Ptr<CLAHE> clahe = createCLAHE();
clahe->setClipLimit(30.0);
clahe->setTilesGridSize(Size(8, 8));
Mat imgray_ad;
clahe->apply(image, imgray_ad);
Mat imgray;
cv::equalizeHist(image, imgray);
imshow("imgray_ad", imgray_ad);
imshow("imgray", imgray);
Mat thresh;
threshold(imgray_ad, thresh, 150, 255, THRESH_BINARY | THRESH_OTSU);
imshow("thresh", thresh);
Mat result;
Mat kernel = Mat::ones(8, 8, CV_8UC1);
erode(thresh, result, kernel);
imshow("result", result);
waitKey();
return 0;
}